Mining video editing rules in video streams

compressed domain processing, transcoding, video editing, MPEG, splicing, reverse play, frame rate conversion, interlace to progressive, motion vector resampling Video compression algorithms are being used to compress digital video for a wide variety of applications, including video delivery over the Internet, advanced television broadcasting, video streaming, video conferencing, and video storage and editing. The impressive performance of modern compression algorithms, combined with the growing availability of video encoders and decoders and low-cost computers, storage devices, and networking equipment, makes it evident that between video capture and video playback, video will be handled in compressed video form. The resulting end-toend compressed digital video systems motivate the need to develop efficient algorithms for handling compressed digital video.

This paper presents a video cut editing rule based on participants' gaze for establishing video editing rules that can accurately and clearly convey the flow of conversation in multiparty conversations to viewers. Demand is growing to be able to effectively archive meetings and teleconferences to facilitate human communication. Conventional systems use fixed-viewpoint cameras and simple camera selection based on participants' utterances etc. However, these systems fail to convey a sufficient amount of nonverbal information about the participants and the flow of conversation. On the basis of participants' gaze behavior in multiparty conversation, we propose a new video cut editing rule; the rule uses majority decision with regard to participants' gaze direction. We then present experiments that compare the proposed method to conventional visual representations. We conclude that the proposed method can more successfully convey 1) who is talking to whom and 2) hearers' response to speakers, which are extremely crucial pieces of information that allow viewers to understand the flow of conversation.

Today's mobile devices enable the users to capture video clips with integrated digital cameras. However, capturing a video clip exactly as intended is often challenging -- in many cases, the possibility to edit the clip after capture would be useful. Earlier we have presented the Mobile Video Editor, an application that allows the users to edit video clips instantly after capture on their mobile devices. In this paper, we describe a field trial that we arranged to further evaluate the Mobile Video Editor concept and to better understand the usage patterns of video editing in the mobile context. The results indicate that especially the teenagers and younger adults found the capability to edit captured video clips a beneficial feature in mobile devices. In addition to being a practical tool to prepare the videos for sharing with others, the Mobile Video Editor was used as a form of entertainment.

The development of real-world ontologies is a complex undertaking, commonly involving a group of domain experts with different expertise that work together in a collaborative setting. These ontologies are usually large scale and have a complex structure. To assist in the authoring process, ontology tools are key at making the editing process as streamlined as possible. Being able to predict confidently what the users are likely to do next as they edit an ontology will enable us to focus and structure the user interface accordingly and to enable more efficient interaction and information discovery. In this paper, we use data mining techniques to investigate whether we are able to predict the next editing operation that a user will make based on the change history. We have analyzed the change logs of two real-world biomedical ontologies, and used association rule mining to find editing patterns using different features. We evaluated the prediction accuracy on a test set of change logs for these two ontologies. Our results indicate that we can indeed predict the next editing operation a user is likely to make. We will use the discovered editing patterns to develop a recommendation module for our editing tools, and to design user interface components that are better fitted with the user editing behaviors.

The trends of data mining on healthcare data for improving medical services have increased because of the electronic healthcare record(EHR) system, which collects a massive amount of data on a daily basis. In the current scenario, hospital maintains its EHR system and stores the detailed information of patients. Data mining for healthcare improvement requires the data from all the EHR systems located at a different location to be stored at the central data mining server. Collection of healthcare data at some untrusted central data mining server raises privacy threats. Healthcare data contains patients’ private information and sharing this information for data mining creates privacy issues. Most of the previous research either focused on k-anonymity technique which causes information loss and decreases data mining accuracy or privacy preserving data mining which is focused on only specific data mining technique. We adopt source anonymous technique as privacy preserving scheme and present a novel scheme for healthcare data collection and mining in this paper. Our scheme collects data from all EHR systems without any information loss and stores at a single central data mining server, also ensuring privacy is preserved. Central data mining server helps to analyze the collected data with different data mining techniques (Association rule mining, Classification, Clustering, etc.) without the involvement of EHR systems. Our scheme is collusion resilient against central data mining server and EHR systems. Theoretical and experimental analysis show the efficiency of our scheme in terms of computation and communication cost. The experimental results using Heart disease dataset show the advantage to EHR systems using the proposed approach in terms of disease prediction accuracy.

The popularity of video social platforms (TikTok, etc.) shows that video is a popular information carrier at present. However, shot occlusion frequently occurs when people are shooting videos to record information. Since the shot occlusion seriously affects the viewers’ experience, the video editors need to find and delete such segments from the video material during post-processing. However, finding the shot occlusion from the video is a time-consuming and laborious task. To reduce the workload of editors, previous researchers proposed a shot occlusion detection algorithm using deep learning technology, which has promotion space in both recognition accuracy and computational efficiency. In this paper, we propose a neural network module, named SAT module, which can effectively extract spatio-temporal information with fewer parameters. We apply SAT module to construct a novel occlusion detection model, and improve the existing occlusion detection loss function for model training. The experimental results on the public dataset show that our method achieves the state-of-the-art performance of 88.25% accuracy and FPS of 130 with the least parameters. Code and models will be available at https://github.com/Junhua-Liao/ICASSP22-OcclusionDetection.

A video-on-demand (VoD) system provides a service which enables a user of the system to request in real time the transmission of a video stream from a collection of available video material. This paper suggests a conceptual model that subclassifies the VoD control and management procedures into three management levels: session, call, and connection. The session management is represented by a finite state machine (FSM) that translates user commands into call layer activities. The states in the session FSM represent active calls between the set-top boxes (STBs) and other entities, whereas the arcs represent distributed protocols for set-up and take-down of calls. This model is used in order to analyze the relationship between the procedures in the various management levels and to discuss the options and trade-offs involved in the design of a VoD session.

Video quality can be measured using both subjective and objective assessment methods. Subjective experiments are crucially important as they constitute a benchmark for evaluating the performance of objective quality metrics. Subjective quality assessment of television pictures has received extensive attention from experts over the past decades. On the other hand, emerging applications such as PC-based video streaming and mobile video streaming require new subjective test methodologies. Although some recent studies have compared different test methodologies and procedures, most concerned television pictures. No studies for multimedia-type video really validated the repeatability and reliability of the assessment method and the experimental procedure. This paper outlines a methodology for conducting subjective evaluation of video quality for multimedia applications in a repeatable and reliable manner across different laboratories. Using video material at low-resolution, low-bit rate and low-frame rate, the same experiment was conducted by two different laboratories, i.e. test material was identical in both experiments. Laboratory set-up was different, i.e. different computers and display panels were used, and viewing distance was not fixed. Results show that quality ratings obtained in both experiments are statistically identical. This is an important validation step for the Video Quality Experts Group, which will conduct an ambitious campaign of subjective experiments using many different test laboratories.

Nowadays, most video material is coded using a non-scalable format. When transmitting these single-layer video bitstreams, there may be a problem for connection links with limited capacity. In order to solve this problem, requantization transcoding is often used. The requantization transcoder applies coarser quantization in order to reduce the amount of residual information in the compressed video bitstream. In this paper, we extend a requantization transcoder for H.264/AVC video bitstreams with a rate-control algorithm. A simple algorithm is proposed which limits the computational complexity. The bit allocation is based on the bit distribution in the original video bitstream. Using the bit budget and a linear model between rate and quantizer, the new quantizer is calculated. The target bit rate is attained with an average deviation lower than 6%, while the rate-distortion performance shows small improvements over transcoding without rate control.

There are usually repetitive sub-segments in broadcast videos, which may be associated with high-level concepts or events, e.g., news footage, repeated scores in basketball. Unsupervised mining techniques provide generic solutions to discovering such temporal patterns in various video genres, which are currently the subject of great interests to researchers working on multimedia content analysis. In this paper, we propose a novel approach to automatically detecting repetitive patterns in a video stream. In this approach, a video stream is first transformed to a symbol sequence via the spectral clustering algorithm. After computing the transition probabilities of any two symbols in temporal evolution, we produce a set of probabilistic templates to characterize the patterns of potential interest. Finally, we verify each probabilistic template by measuring the similarities between the video sub-segments and the template. Evaluations on various sports videos show promising results.

Multimedia information is ubiquitous and essential in many applications from homeland security to medicine and bioinformatics. As evidenced by the success of the previous editions of MDM/KDD, there is an increasing need in new techniques and tools that can detect and discover patterns, in multimedia data, that can lead to new knowledge. For example, tools are needed for discovering relationships between objects or segments within images, classifying images based on their content, extracting patterns in sound, categorizing speech and music, and recognizing and tracking objects in video streams. There is also an increasing interest in the real-time analysis of multimedia data generated by distributed sensory applications and ambient intelligence environments.MDM is a leading venue where researchers, both from the academia and industry, can exchange and compare both relatively mature and green house theories, methodologies, algorithms and frameworks for multimedia data mining. To address this aim, the workshop brings together experts in the analysis of digital media content, multimedia databases, multimedia information retrieval, and domain experts from different applied disciplines with potential in multimedia data mining and knowledge discovery. The previous seven workshops have been held in conjunction with KDD 2000 (Boston, MA), KDD2001 (San Francisco, CA), KDD 2002 (Edmonton, Canada), KDD 2003 (Washington, DC), KDD 2004 (Seattle, WA), KDD 2005 (Chicago, IL), and KDD 2006 (Philadelphia, PA) respectively. Like the previous editions, MDM 2007 aimed at facilitating cross-disciplinary exchange of ideas.MDM 2007 contains six regular papers focusing on various aspects of multimedia data mining, including content-supported learning of user preferences, integration of multiple visual learners for media mining, salient-point based image object detection, the use of relevance feedback for video event mining, association rule mining for infrequent database items, and a novel algebra for supporting ranked data processing in multimedia mining applications. In addition, we have invited two leading researchers to present their views on major challenges faced by the multimedia data mining community: The invited talk by Dr. Belle Tseng from NEC Labs, America, focuses on the problem of temporal graph mining and its applications to blog analysis. Prof. Keogh from University of California, Riverside, on the other hand, highlights the challenges faced by the data mining community due to frequently non-reproducible results published at the best data mining conferences.We are thankful to the authors who have submitted papers to the workshop, to our invited speakers, to the PC members and reviewers who all have done a fabulous job, to KDD 2007 organizers (especially to Qiang Yang from University of Science and Technology, Hong Kong for his support to the workshop and to Scott Gaffney for his help with the proceedings).

Indonesian EITI (Extractive Industries Transparency Initiative) is an organization under Ministry of Economic Coordination which used to increase the transparency of extractive industry in Indonesia. EITI Indonesia manage a lot of data about mining, one of the managed data is data Mining Business License in Indonesia. The data has many records that require large storage allocation and difficult process data that is used by the EITI for decision making. . This data Mining Business License will be used for the processing of data mining that aims to help look for interesting patterns to determine a learning and two itemsets (attributes) that exist. Application Data Mining with Emerging Patterns Supervised methods will be used as a solution for managing data such large, so it is easy to produce a decision in the form of an interesting pattern information to determine the transparency of mining license in Indonesia. System development methods using CRISP-DM. The design of data mining applications using the programming language Java, NetBeans and MySQL database tools used to build a technology Supervised Emerging Patterns in multi-attribute decision making.

DEFINING TEXT MINING Text mining can be broadly defined as a knowledge-intensive process in which a user interacts with a document collection over time by using a suite of analysis tools. In a manner analogous to data mining, text mining seeks to extract useful information from data sources through the identification and exploration of interesting patterns. In the case of text mining, however, the data sources are document collections, and interesting patterns are found not among formalized database records but in the unstructured textual data in the documents in these collections. Certainly, text mining derives much of its inspiration and direction from seminal research on data mining. Therefore, it is not surprising to find that text mining and data mining systems evince many high-level architectural similarities. For instance, both types of systems rely on preprocessing routines, pattern-discovery algorithms, and presentation-layer elements such as visualization tools to enhance the browsing of answer sets. Further, text mining adopts many of the specific types of patterns in its core knowledge discovery operations that were first introduced and vetted in data mining research. Because data mining assumes that data have already been stored in a structured format, much of its preprocessing focus falls on two critical tasks: Scrubbing and normalizing data and creating extensive numbers of table joins. In contrast, for text mining systems, preprocessing operations center on the identification and extraction of representative features for natural language documents.

Neural networks has been widely used in data mining, but the main challenge of it is to get high efficiency and explicit knowledge. So a BDB neural network is proposed to improve the efficiency in the paper. Meanwhile, an improved genetic algorithm, which can enhance ability of selecting fitness, for rule extraction from artificial neural networks is adopted. Compared with other data mining measures, the developed algorithm shows higher performance in efficiency and accuracy.

Data mining is the process of posing queries and extracting patterns, often previously unknown from large quantities of data using pattern matching or other reasoning techniques. Data mining has many applications in security including for national security as well as for cyber security. The threats to national security include attacking buildings, destroying critical infrastructures such as power grids and telecommunication systems. Data mining techniques are being investigated to find out who the suspicious people are and who is capable of carrying out terrorist activities. Cyber security is involved with protecting the computer and network systems against corruption due to Trojan horses, worms and viruses. Data mining is also being applied to provide solutions such as intrusion detection and auditing. The first part of the presentation will discuss my joint research with Prof. Latifur Khan and our students at the University of Texas at Dallas on data mining for cyber security applications For example; anomaly detection techniques could be used to detect unusual patterns and behaviors. Link analysis may be used to trace the viruses to the perpetrators. Classification may be used to group various cyber attacks and then use the profiles to detect an attack when it occurs. Prediction may be used to determine potential future attacks depending in a way on information learnt about terrorists through email and phone conversations. Data mining is also being applied for intrusion detection and auditing. Other applications include data mining for malicious code detection such as worm detection and managing firewall policies. This second part of the presentation will discuss the various types of threats to national security and describe data mining techniques for handling such threats. Threats include non real-time threats and real-time threats. We need to understand the types of threats and also gather good data to carry out mining and obtain useful results. The challenge is to reduce false positives and false negatives. The third part of the presentation will discuss some of the research challenges. We need some form of real-time data mining, that is, the results have to be generated in real-time, we also need to build models in real-time for realtime intrusion detection. Data mining is also being applied for credit card fraud detection and biometrics related applications. While some progress has been made on topics such as stream data mining, there is still a lot of work to be done here. Another challenge is to mine multimedia data including surveillance video. Finally, we need to maintain the privacy of individuals. Much research has been carried out on privacy preserving data mining. In summary, the presentation will provide an overview of data mining, the various types of threats and then discuss the applications of data mining for malicious code detection, cyber security and national security. Then we will discuss the consequences to privacy.